[English] 日本語
Yorodumi
- PDB-8f53: Top-down design of protein architectures with reinforcement learning -

+
Open data


ID or keywords:

Loading...

-
Basic information

Entry
Database: PDB / ID: 8f53
TitleTop-down design of protein architectures with reinforcement learning
ComponentsRC_I_2
KeywordsDE NOVO PROTEIN / nanoparticle / capsid / oligomer / de novo design / rosetta / reinforcement learning
Biological speciessynthetic construct (others)
MethodELECTRON MICROSCOPY / single particle reconstruction / cryo EM / Resolution: 2.93 Å
AuthorsBorst, A.J. / Baker, D.
Funding support United States, 1items
OrganizationGrant numberCountry
Howard Hughes Medical Institute (HHMI) United States
CitationJournal: Science / Year: 2023
Title: Top-down design of protein architectures with reinforcement learning.
Authors: Isaac D Lutz / Shunzhi Wang / Christoffer Norn / Alexis Courbet / Andrew J Borst / Yan Ting Zhao / Annie Dosey / Longxing Cao / Jinwei Xu / Elizabeth M Leaf / Catherine Treichel / Patrisia ...Authors: Isaac D Lutz / Shunzhi Wang / Christoffer Norn / Alexis Courbet / Andrew J Borst / Yan Ting Zhao / Annie Dosey / Longxing Cao / Jinwei Xu / Elizabeth M Leaf / Catherine Treichel / Patrisia Litvicov / Zhe Li / Alexander D Goodson / Paula Rivera-Sánchez / Ana-Maria Bratovianu / Minkyung Baek / Neil P King / Hannele Ruohola-Baker / David Baker /
Abstract: As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function ...As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function in a manner not achievable by current design approaches. We describe a "top-down" reinforcement learning-based design approach that solves this problem using Monte Carlo tree search to sample protein conformers in the context of an overall architecture and specified functional constraints. Cryo-electron microscopy structures of the designed disk-shaped nanopores and ultracompact icosahedra are very close to the computational models. The icosohedra enable very-high-density display of immunogens and signaling molecules, which potentiates vaccine response and angiogenesis induction. Our approach enables the top-down design of complex protein nanomaterials with desired system properties and demonstrates the power of reinforcement learning in protein design.
History
DepositionNov 11, 2022Deposition site: RCSB / Processing site: RCSB
Revision 1.0May 10, 2023Provider: repository / Type: Initial release
Revision 1.1Jun 19, 2024Group: Data collection / Category: chem_comp_atom / chem_comp_bond

-
Structure visualization

Structure viewerMolecule:
MolmilJmol/JSmol

Downloads & links

-
Assembly

Deposited unit
A: RC_I_2
F: RC_I_2
K: RC_I_2
U: RC_I_2
J1: RC_I_2
Od: RC_I_2
Tc: RC_I_2
Ba: RC_I_2
B: RC_I_2
G: RC_I_2
L: RC_I_2
V: RC_I_2
Z: RC_I_2
Id: RC_I_2
Nh: RC_I_2
Sl: RC_I_2
Xp: RC_I_2
Yb: RC_I_2
C: RC_I_2
H: RC_I_2
M: RC_I_2
W: RC_I_2
Ca: RC_I_2
He: RC_I_2
Mi: RC_I_2
Rm: RC_I_2
Wq: RC_I_2
Ae: RC_I_2
D: RC_I_2
I: RC_I_2
N: RC_I_2
X: RC_I_2
Bb: RC_I_2
Gf: RC_I_2
Lj: RC_I_2
Qn: RC_I_2
Vr: RC_I_2
Zt: RC_I_2
E: RC_I_2
J: RC_I_2
O: RC_I_2
Y: RC_I_2
Dc: RC_I_2
Fg: RC_I_2
Kk: RC_I_2
Po: RC_I_2
Us: RC_I_2
Hu: RC_I_2
P: RC_I_2
Gv: RC_I_2
Q: RC_I_2
Fw: RC_I_2
R: RC_I_2
Ex: RC_I_2
S: RC_I_2
Dy: RC_I_2
T: RC_I_2
Cz: RC_I_2
0: RC_I_2
2: RC_I_2


Theoretical massNumber of molelcules
Total (without water)353,15860
Polymers353,15860
Non-polymers00
Water00
1


  • Idetical with deposited unit
  • defined by author
  • Evidence: electron microscopy, negative stain EM, cryo-EM
TypeNameSymmetry operationNumber
identity operation1_5551

-
Components

#1: Protein ...
RC_I_2


Mass: 5885.969 Da / Num. of mol.: 60
Source method: isolated from a genetically manipulated source
Source: (gene. exp.) synthetic construct (others) / Production host: Escherichia coli (E. coli)

-
Experimental details

-
Experiment

ExperimentMethod: ELECTRON MICROSCOPY
EM experimentAggregation state: PARTICLE / 3D reconstruction method: single particle reconstruction

-
Sample preparation

ComponentName: RC_I_2 / Type: COMPLEX / Entity ID: all / Source: RECOMBINANT
Source (natural)Organism: Escherichia coli (E. coli)
Source (recombinant)Organism: Escherichia coli (E. coli)
Buffer solutionpH: 7.5
SpecimenConc.: 0.5 mg/ml / Embedding applied: NO / Shadowing applied: NO / Staining applied: NO / Vitrification applied: YES
Specimen supportGrid type: Quantifoil R2/2
VitrificationCryogen name: ETHANE

-
Electron microscopy imaging

Experimental equipment
Model: Titan Krios / Image courtesy: FEI Company
MicroscopyModel: TFS KRIOS
Electron gunElectron source: FIELD EMISSION GUN / Accelerating voltage: 300 kV / Illumination mode: FLOOD BEAM
Electron lensMode: BRIGHT FIELD / Nominal defocus max: 1700 nm / Nominal defocus min: 800 nm
Image recordingElectron dose: 61.5 e/Å2 / Detector mode: COUNTING / Film or detector model: GATAN K3 (6k x 4k)

-
Processing

SoftwareName: PHENIX / Version: 1.20.1_4487: / Classification: refinement
EM software
IDNameVersionCategory
7Rosettamodel fitting
8Cootmodel fitting
9ISOLDEmodel fitting
10PHENIXmodel fitting
12cryoSPARC3.2initial Euler assignment
13cryoSPARC3.2final Euler assignment
15cryoSPARC3.23D reconstruction
16Rosettamodel refinement
17Cootmodel refinement
18ISOLDEmodel refinement
19PHENIXmodel refinement
CTF correctionType: NONE
Particle selectionNum. of particles selected: 897978
3D reconstructionResolution: 2.93 Å / Resolution method: FSC 0.143 CUT-OFF / Num. of particles: 325728 / Symmetry type: POINT
Refine LS restraints
Refine-IDTypeDev idealNumber
ELECTRON MICROSCOPYf_bond_d0.00224660
ELECTRON MICROSCOPYf_angle_d0.41132940
ELECTRON MICROSCOPYf_dihedral_angle_d11.8189540
ELECTRON MICROSCOPYf_chiral_restr0.0324080
ELECTRON MICROSCOPYf_plane_restr0.0024080

+
About Yorodumi

-
News

-
Feb 9, 2022. New format data for meta-information of EMDB entries

New format data for meta-information of EMDB entries

  • Version 3 of the EMDB header file is now the official format.
  • The previous official version 1.9 will be removed from the archive.

Related info.:EMDB header

External links:wwPDB to switch to version 3 of the EMDB data model

-
Aug 12, 2020. Covid-19 info

Covid-19 info

URL: https://pdbj.org/emnavi/covid19.php

New page: Covid-19 featured information page in EM Navigator.

Related info.:Covid-19 info / Mar 5, 2020. Novel coronavirus structure data

+
Mar 5, 2020. Novel coronavirus structure data

Novel coronavirus structure data

Related info.:Yorodumi Speices / Aug 12, 2020. Covid-19 info

External links:COVID-19 featured content - PDBj / Molecule of the Month (242)：Coronavirus Proteases

+
Jan 31, 2019. EMDB accession codes are about to change! (news from PDBe EMDB page)

EMDB accession codes are about to change! (news from PDBe EMDB page)

  • The allocation of 4 digits for EMDB accession codes will soon come to an end. Whilst these codes will remain in use, new EMDB accession codes will include an additional digit and will expand incrementally as the available range of codes is exhausted. The current 4-digit format prefixed with “EMD-” (i.e. EMD-XXXX) will advance to a 5-digit format (i.e. EMD-XXXXX), and so on. It is currently estimated that the 4-digit codes will be depleted around Spring 2019, at which point the 5-digit format will come into force.
  • The EM Navigator/Yorodumi systems omit the EMD- prefix.

Related info.:Q: What is EMD? / ID/Accession-code notation in Yorodumi/EM Navigator

External links:EMDB Accession Codes are Changing Soon! / Contact to PDBj

+
Jul 12, 2017. Major update of PDB

Major update of PDB

  • wwPDB released updated PDB data conforming to the new PDBx/mmCIF dictionary.
  • This is a major update changing the version number from 4 to 5, and with Remediation, in which all the entries are updated.
  • In this update, many items about electron microscopy experimental information are reorganized (e.g. em_software).
  • Now, EM Navigator and Yorodumi are based on the updated data.

External links:wwPDB Remediation / Enriched Model Files Conforming to OneDep Data Standards Now Available in the PDB FTP Archive

-
Yorodumi

Thousand views of thousand structures

  • Yorodumi is a browser for structure data from EMDB, PDB, SASBDB, etc.
  • This page is also the successor to EM Navigator detail page, and also detail information page/front-end page for Omokage search.
  • The word "yorodu" (or yorozu) is an old Japanese word meaning "ten thousand". "mi" (miru) is to see.

Related info.:EMDB / PDB / SASBDB / Comparison of 3 databanks / Yorodumi Search / Aug 31, 2016. New EM Navigator & Yorodumi / Yorodumi Papers / Jmol/JSmol / Function and homology information / Changes in new EM Navigator and Yorodumi

Read more